© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 9178
    Prev
    Next
    INDEX
    Explanations

    the presence of a specific numerical value or statistic

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows punctuation or a short word

    np_acts-logits-general · gemini-2.0-flash

    program / technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+
    -0.65
     disambiguazione
    -0.65
     архивлан
    -0.65
    الحياه
    -0.61
    UnsafeEnabled
    -0.59
    Спасылкі
    -0.59
    ValueStyle
    -0.59
     defStyleAttr
    -0.57
    IndentedString
    -0.57
    Зноскі
    -0.55
    POSITIVE LOGITS
    Autoritní
    0.59
    REACT
    0.58
    阔
    0.55
    AutoScaleMode
    0.53
    SequentialGroup
    0.52
    <%@
    0.51
    gea
    0.51
    --
    
    0.51
    CreateModel
    0.51
     démocratie
    0.50
    Activations Density 0.046%

    No Known Activations